Conference on Learning for Dynamics & Control最新文献_第3页

Regret Analysis of Online LQR Control via Trajectory Prediction and Tracking: Extended Version 基于轨迹预测与跟踪的在线LQR控制的后悔分析:扩展版

Conference on Learning for Dynamics & Control Pub Date : 2023-02-21 DOI: 10.48550/arXiv.2302.10411

Yitian Chen, Timothy L. Molloy, T. Summers, I. Shames

引用次数: 1

Modified Policy Iteration for Exponential Cost Risk Sensitive MDPs 指数成本风险敏感mdp的改进策略迭代

Conference on Learning for Dynamics & Control Pub Date : 2023-02-08 DOI: 10.48550/arXiv.2302.03811

Yashaswini Murthy, Mehrdad Moharrami, R. Srikant

引用次数: 0

Certified Invertibility in Neural Networks via Mixed-Integer Programming 基于混合整数规划的神经网络的证明可逆性

Conference on Learning for Dynamics & Control Pub Date : 2023-01-27 DOI: 10.48550/arXiv.2301.11783

Tianqi Cui, Tom S. Bertalan, George J. Pappas, M. Morari, I. Kevrekidis, Mahyar Fazlyab

引用次数: 0

Online switching control with stability and regret guarantees 在线切换控制，具有稳定性和遗憾保证

Conference on Learning for Dynamics & Control Pub Date : 2023-01-20 DOI: 10.48550/arXiv.2301.08445

Yingying Li, James A. Preiss, Na Li, Yiheng Lin, A. Wierman, J. Shamma

引用次数: 4

Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control? 直接潜模型学习能解决线性二次高斯控制吗?

Conference on Learning for Dynamics & Control Pub Date : 2022-12-30 DOI: 10.48550/arXiv.2212.14511

Yi Tian, K. Zhang, Russ Tedrake, S. Sra

{"title":"Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?","authors":"Yi Tian, K. Zhang, Russ Tedrake, S. Sra","doi":"10.48550/arXiv.2212.14511","DOIUrl":"https://doi.org/10.48550/arXiv.2212.14511","url":null,"abstract":"We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system. We pursue a direct latent model learning approach, where a dynamic model in some latent state space is learned by predicting quantities directly related to planning (e.g., costs) without reconstructing the observations. In particular, we focus on an intuitive cost-driven state representation learning method for solving Linear Quadratic Gaussian (LQG) control, one of the most fundamental partially observable control problems. As our main results, we establish finite-sample guarantees of finding a near-optimal state representation function and a near-optimal controller using the directly learned latent model. To the best of our knowledge, despite various empirical successes, prior to this work it was unclear if such a cost-driven latent model learner enjoys finite-sample guarantees. Our work underscores the value of predicting multi-step costs, an idea that is key to our theory, and notably also an idea that is known to be empirically valuable for learning state representations.","PeriodicalId":268449,"journal":{"name":"Conference on Learning for Dynamics & Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130463164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Data-driven Stochastic Output-Feedback Predictive Control: Recursive Feasibility through Interpolated Initial Conditions 数据驱动的随机输出反馈预测控制:通过插值初始条件的递归可行性

Conference on Learning for Dynamics & Control Pub Date : 2022-12-15 DOI: 10.48550/arXiv.2212.07661

Guanru Pan, Ruchuan Ou, T. Faulwasser

{"title":"Data-driven Stochastic Output-Feedback Predictive Control: Recursive Feasibility through Interpolated Initial Conditions","authors":"Guanru Pan, Ruchuan Ou, T. Faulwasser","doi":"10.48550/arXiv.2212.07661","DOIUrl":"https://doi.org/10.48550/arXiv.2212.07661","url":null,"abstract":"The paper investigates data-driven output-feedback predictive control of linear systems subject to stochastic disturbances. The scheme relies on the recursive solution of a suitable data-driven reformulation of a stochastic Optimal Control Problem (OCP), which allows for forward prediction and optimization of statistical distributions of inputs and outputs. Our approach avoids the use of parametric system models. Instead it is based on previously recorded data using a recently proposed stochastic variant of Willems' fundamental lemma. The stochastic variant of the lemma is applicable to a large class of linear dynamics subject to stochastic disturbances of Gaussian and non-Gaussian nature. To ensure recursive feasibility, the initial condition of the OCP -- which consists of information about past inputs and outputs -- is considered as an extra decision variable of the OCP. We provide sufficient conditions for recursive feasibility and closed-loop practical stability of the proposed scheme as well as performance bounds. Finally, a numerical example illustrates the efficacy and closed-loop properties of the proposed scheme.","PeriodicalId":268449,"journal":{"name":"Conference on Learning for Dynamics & Control","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122146886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems 基于混合多智能体的随需移动系统深度强化学习

Conference on Learning for Dynamics & Control Pub Date : 2022-12-14 DOI: 10.48550/arXiv.2212.07313

Tobias Enders, James Harrison, M. Pavone, Maximilian Schiffer

引用次数: 5

Learning Disturbances Online for Risk-Aware Control: Risk-Aware Flight with Less Than One Minute of Data 在线学习干扰风险感知控制:风险感知飞行少于一分钟的数据

Conference on Learning for Dynamics & Control Pub Date : 2022-12-12 DOI: 10.48550/arXiv.2212.06253

Prithvi Akella, Skylar X. Wei, J. Burdick, A. Ames

引用次数: 2

Targeted Adversarial Attacks against Neural Network Trajectory Predictors 针对神经网络轨迹预测器的针对性对抗性攻击

Conference on Learning for Dynamics & Control Pub Date : 2022-12-08 DOI: 10.48550/arXiv.2212.04138

Kai Liang Tan, J. Wang, Y. Kantaros

{"title":"Targeted Adversarial Attacks against Neural Network Trajectory Predictors","authors":"Kai Liang Tan, J. Wang, Y. Kantaros","doi":"10.48550/arXiv.2212.04138","DOIUrl":"https://doi.org/10.48550/arXiv.2212.04138","url":null,"abstract":"Trajectory prediction is an integral component of modern autonomous systems as it allows for envisioning future intentions of nearby moving agents. Due to the lack of other agents' dynamics and control policies, deep neural network (DNN) models are often employed for trajectory forecasting tasks. Although there exists an extensive literature on improving the accuracy of these models, there is a very limited number of works studying their robustness against adversarially crafted input trajectories. To bridge this gap, in this paper, we propose a targeted adversarial attack against DNN models for trajectory forecasting tasks. We call the proposed attack TA4TP for Targeted adversarial Attack for Trajectory Prediction. Our approach generates adversarial input trajectories that are capable of fooling DNN models into predicting user-specified target/desired trajectories. Our attack relies on solving a nonlinear constrained optimization problem where the objective function captures the deviation of the predicted trajectory from a target one while the constraints model physical requirements that the adversarial input should satisfy. The latter ensures that the inputs look natural and they are safe to execute (e.g., they are close to nominal inputs and away from obstacles). We demonstrate the effectiveness of TA4TP on two state-of-the-art DNN models and two datasets. To the best of our knowledge, we propose the first targeted adversarial attack against DNN models used for trajectory forecasting.","PeriodicalId":268449,"journal":{"name":"Conference on Learning for Dynamics & Control","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115571068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Concentration Phenomenon for Random Dynamical Systems: An Operator Theoretic Approach 随机动力系统的集中现象:一种算子理论方法

Conference on Learning for Dynamics & Control Pub Date : 2022-12-07 DOI: 10.48550/arXiv.2212.03670

Muhammad Naeem

{"title":"Concentration Phenomenon for Random Dynamical Systems: An Operator Theoretic Approach","authors":"Muhammad Naeem","doi":"10.48550/arXiv.2212.03670","DOIUrl":"https://doi.org/10.48550/arXiv.2212.03670","url":null,"abstract":"Via operator theoretic methods, we formalize the concentration phenomenon for a given observable `$r$' of a discrete time Markov chain with `$mu_{pi}$' as invariant ergodic measure, possibly having support on an unbounded state space. The main contribution of this paper is circumventing tedious probabilistic methods with a study of a composition of the Markov transition operator $P$ followed by a multiplication operator defined by $e^{r}$. It turns out that even if the observable/ reward function is unbounded, but for some for some $q>2$, $|e^{r}|_{q rightarrow 2} propto expbig(mu_{pi}(r) +frac{2q}{q-2}big) $ and $P$ is hyperbounded with norm control $|P|_{2 rightarrow q }<e^{frac{1}{2}[frac{1}{2}-frac{1}{q}]}$, sharp non-asymptotic concentration bounds follow. emph{Transport-entropy} inequality ensures the aforementioned upper bound on multiplication operator for all $q>2$. The role of emph{reversibility} in concentration phenomenon is demystified. These results are particularly useful for the reinforcement learning and controls communities as they allow for concentration inequalities w.r.t standard unbounded obersvables/reward functions where exact knowledge of the system is not available, let alone the reversibility of stationary measure.","PeriodicalId":268449,"journal":{"name":"Conference on Learning for Dynamics & Control","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125311900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1